In recent years, frequent violations by publicly listed companies in China have eroded market trust. This study employs traditional financial and non-financial metrics, emerging ESG metrics, and composite indicators c...
详细信息
According to the principles of security management, intuitive scientificity, and scalability, an information security system architecture based on representation and metric deep learning algorithms was designed. Two k...
详细信息
Federated learning is a distributed machine learning approach that utilizes multiple devices' coordination for training purposes. Nevertheless, distributed computing tends to result in slow training. It is importa...
详细信息
Automated Image Colorization aims to convert black-and-white images into color using deep learning algorithms. This innovative approach relies on the power of convolutional neural networks (CNN) specifically designed ...
详细信息
Electro-erosion wear (EEW) is a significant problem in the mold steel industry, as it can greatly reduce the lifespan of electrodes. This study presents a machine-learning approach for predicting and modeling electrod...
详细信息
This paper explores the relationship between the changes in facial expressions and actions of patients with depression and the outcome of their symptoms and internal psychological integration based on deep learning al...
详细信息
A Spiking Neural Network (SNN) processes neural information through precise timing of spikes and is considered a brain-inspired computational model of the third generation of the artificial neural network. SNN has a s...
详细信息
When two different parties use the same learning rule on their own data, how can we test whether the distributions of the two outcomes are similar? In this paper, we study the similarity of outcomes of learning rules ...
详细信息
When two different parties use the same learning rule on their own data, how can we test whether the distributions of the two outcomes are similar? In this paper, we study the similarity of outcomes of learning rules through the lens of the Total Variation (TV) distance of distributions. We say that a learning rule is TV indistinguishable if the expected TV distance between the posterior distributions of its outputs, executed on two training data sets drawn independently from the same distribution, is small. We first investigate the learnability of hypothesis classes using TV indistinguishable learners. Our main results are information-theoretic equivalences between TV indistinguishability and existing algorithmic stability notions such as replicability and approximate differential privacy. Then, we provide statistical amplification and boosting algorithms for TV indistinguishable learners.
The personality is considered as the combination of various factors including behavior, emotion, thoughts, etc. It has a crucial impact on our daily life. Many works in the literature proposed solutions to study the d...
详细信息
Deep learning algorithms have emerged as powerful tools for various applications, including image recognition, natural language processing, and data analysis. With a multitude of deep learning algorithms available, it...
详细信息
暂无评论